OV - exec - Loop 716

	Loop Id: 716	Module: exec	Source: BsplineFunctor.h:291-297	Coverage: 0.02%

0x4370dc LDR	D24, [X17, X0,LSL #3]    [16]

0x4370e0 FCMPE	D8, D24

0x4370e4 B.LS	437104

0x4370e8 ADD	W30, W13, W0

0x4370ec CMP	W30, W25

0x4370f0 B.EQ	437104

0x4370f4 ORR	W18, WZR, W6

0x4370f8 ADD	W6, W6, #1

0x4370fc STR	W0, [X20, X18,LSL #2]    [18]

0x437100 STR	D24, [X19, X18,LSL #3]    [10]

0x437104 ADD	X0, X0, #1

0x437108 LDR	D15, [X17, X0,LSL #3]    [2]

0x43710c FCMPE	D8, D15

0x437110 B.LS	437130

0x437114 ADD	W30, W13, W0

0x437118 CMP	W30, W25

0x43711c B.EQ	437130

0x437120 ORR	W18, WZR, W6

0x437124 ADD	W6, W6, #1

0x437128 STR	W0, [X20, X18,LSL #2]    [17]

0x43712c STR	D15, [X19, X18,LSL #3]    [9]

0x437130 ADD	X18, X0, #1

0x437134 LDR	D17, [X17, X18,LSL #3]    [12]

0x437138 FCMPE	D8, D17

0x43713c B.LS	43715c

0x437140 ADD	W30, W13, W18

0x437144 CMP	W30, W25

0x437148 B.EQ	43715c

0x43714c ORR	W30, WZR, W6

0x437150 ADD	W6, W6, #1

0x437154 STR	W18, [X20, X30,LSL #2]    [15]

0x437158 STR	D17, [X19, X30,LSL #3]    [8]

0x43715c ADD	X18, X0, #2

0x437160 LDR	D28, [X17, X18,LSL #3]    [1]

0x437164 FCMPE	D8, D28

0x437168 B.LS	437188

0x43716c ADD	W30, W13, W18

0x437170 CMP	W30, W25

0x437174 B.EQ	437188

0x437178 ORR	W30, WZR, W6

0x43717c ADD	W6, W6, #1

0x437180 STR	W18, [X20, X30,LSL #2]    [14]

0x437184 STR	D28, [X19, X30,LSL #3]    [7]

0x437188 ADD	X18, X0, #3

0x43718c LDR	D22, [X17, X18,LSL #3]    [11]

0x437190 FCMPE	D8, D22

0x437194 B.LS	4371b4

0x437198 ADD	W30, W13, W18

0x43719c CMP	W30, W25

0x4371a0 B.EQ	4371b4

0x4371a4 ORR	W30, WZR, W6

0x4371a8 ADD	W6, W6, #1

0x4371ac STR	W18, [X20, X30,LSL #2]    [13]

0x4371b0 STR	D22, [X19, X30,LSL #3]    [6]

0x4371b4 ADD	X18, X0, #4

0x4371b8 LDR	D21, [X17, X18,LSL #3]    [19]

0x4371bc FCMPE	D8, D21

0x4371c0 B.LS	4371e0

0x4371c4 ADD	W30, W13, W18

0x4371c8 CMP	W30, W25

0x4371cc B.EQ	4371e0

0x4371d0 ORR	W30, WZR, W6

0x4371d4 ADD	W6, W6, #1

0x4371d8 STR	W18, [X20, X30,LSL #2]    [5]

0x4371dc STR	D21, [X19, X30,LSL #3]    [24]

0x4371e0 ADD	X18, X0, #5

0x4371e4 LDR	D12, [X17, X18,LSL #3]    [20]

0x4371e8 FCMPE	D8, D12

0x4371ec B.LS	43720c

0x4371f0 ADD	W30, W13, W18

0x4371f4 CMP	W30, W25

0x4371f8 B.EQ	43720c

0x4371fc ORR	W30, WZR, W6

0x437200 ADD	W6, W6, #1

0x437204 STR	W18, [X20, X30,LSL #2]    [4]

0x437208 STR	D12, [X19, X30,LSL #3]    [23]

0x43720c ADD	X18, X0, #6

0x437210 LDR	D30, [X17, X18,LSL #3]    [21]

0x437214 FCMPE	D8, D30

0x437218 B.LS	437238

0x43721c ADD	W30, W13, W18

0x437220 CMP	W30, W25

0x437224 B.EQ	437238

0x437228 ORR	W30, WZR, W6

0x43722c ADD	W6, W6, #1

0x437230 STR	W18, [X20, X30,LSL #2]    [3]

0x437234 STR	D30, [X19, X30,LSL #3]    [22]

0x437238 ADD	X0, X0, #7

0x43723c CMP	X1, X0

0x437240 B.NE	4370dc

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 297

--------------------------------------------------------------------------------

291:   for (int jat = 0; jat < iLimit; jat++)

292:   {

293:     real_type r = distArray[jat];

294:     if (r < cutoff_radius && iStart + jat != iat)

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

Coverage (%)	Name	Source Location	Module

Path /

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)
Source	BsplineFunctor.h:291-297
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	14.22
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)
Source	BsplineFunctor.h:291-297
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	14.22
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	miniqmcreference::TwoBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)
Source file and lines	BsplineFunctor.h:291-297
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-297.

The related source loop is multi-versionned.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6561 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 11.25 to 5.33 cycles (2.11x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your loop is not vectorized. Only 18% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 11.25 to 1.67 cycles (6.75x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Execution ports to units layout:

P0:
P1:
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 4370dc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D24, [X17, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D24	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437104 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x444>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437104 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x444>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W18, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X20, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D24, [X19, X18,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X17, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D15	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437130 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x470>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437130 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x470>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W18, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X20, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X19, X18,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D17	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 43715c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43715c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D28, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D28	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437188 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437188 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D28, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D22, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D22	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 4371b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4371b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D22, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D21, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D21	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 4371e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x520>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4371e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x520>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D21, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D12	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 43720c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43720c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D30, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D30	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437238 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x578>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437238 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x578>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D30, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X1, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 4370dc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x41c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)
Source file and lines	BsplineFunctor.h:291-297
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-297.

The related source loop is multi-versionned.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 11.25 to 5.33 cycles (2.11x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Execution ports to units layout:

P0:
P1:
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 4370dc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D24, [X17, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D24	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437104 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x444>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437104 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x444>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W18, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X20, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D24, [X19, X18,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X17, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D15	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437130 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x470>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437130 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x470>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W18, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X20, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X19, X18,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D17	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 43715c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43715c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D28, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D28	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437188 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437188 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D28, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D22, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D22	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 4371b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4371b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D22, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D21, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D21	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 4371e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x520>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4371e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x520>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D21, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D12	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 43720c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43720c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X18, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D30, [X17, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D30	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 437238 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x578>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W13, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 437238 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x578>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W30, WZR, W6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W6, W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W18, [X20, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D30, [X19, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X1, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 4370dc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x41c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Matching between your loop (in the source code) and the binary loop

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Matching between your loop (in the source code) and the binary loop

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code